Frame-Level Multi-Label Playing Technique Detection Using Multi-Scale Network and Self-Attention Mechanism

TL;DR

This paper introduces a novel multi-scale network with self-attention for frame-level multi-label playing technique detection in polyphonic Guzheng music, addressing overlapping techniques and creating a new annotated dataset.

Contribution

It presents a new multi-scale network with self-attention for IPT detection and introduces the Guzheng_Tech99 dataset for polyphonic instrumental analysis.

Findings

Outperforms existing IPT detection methods significantly

Effective in detecting overlapping and long-range IPTs

Demonstrates robustness on Guzheng recordings

Abstract

Instrument playing technique (IPT) is a key element of musical presentation. However, most of the existing works for IPT detection only concern monophonic music signals, yet little has been done to detect IPTs in polyphonic instrumental solo pieces with overlapping IPTs or mixed IPTs. In this paper, we formulate it as a frame-level multi-label classification problem and apply it to Guzheng, a Chinese plucked string instrument. We create a new dataset, Guzheng\_Tech99, containing Guzheng recordings and onset, offset, pitch, IPT annotations of each note. Because different IPTs vary a lot in their lengths, we propose a new method to solve this problem using multi-scale network and self-attention. The multi-scale network extracts features from different scales, and the self-attention mechanism applied to the feature maps at the coarsest scale further enhances the long-range feature extraction. Our approach outperforms existing works by a large margin, indicating its effectiveness in IPT detection.